Triple
T4234701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daytona Beach International Airport |
E94664
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object | Runway 7L/25R |
E87182
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Runway 7L/25R | Statement: [Daytona Beach International Airport, hasRunway, Runway 7L/25R]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway 7L/25R Context triple: [Daytona Beach International Airport, hasRunway, Runway 7L/25R]
-
A.
Runway 07L/25R
chosen
Runway 07L/25R is a designated airport runway forming one of a pair of parallel runways used for aircraft takeoffs and landings.
-
B.
Runway 7/25
Runway 7/25 is a primary paved runway at Reno–Tahoe International Airport used for commercial and general aviation takeoffs and landings.
-
C.
Runway 17L/35R
Runway 17L/35R is one of the main paved runways at Lyon–Saint-Exupéry Airport in France, used for both domestic and international air traffic operations.
-
D.
Runway 17L/35R
Runway 17L/35R is one of the primary paved runways at Orlando International Airport, used for handling both commercial and general aviation traffic.
-
E.
Runway 17L/35R
Runway 17L/35R is a primary paved runway at North Texas Regional Airport used for general aviation and regional air traffic operations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69b34537cc6481909cd0a96acbb33ef7 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e6705548190b695b3789d713b4a |
completed | March 12, 2026, 11:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bfd70b4a7c8190852503f31142562e |
completed | March 22, 2026, 11:48 a.m. |
Created at: March 12, 2026, 11:05 p.m.